improve

Capture session learnings and propose skill improvements from conversation history.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/lzlatkin/dots --skill improve-lzlatkin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: improve
Source: https://github.com/lzlatkin/dots/tree/main/agents/skills/improve
Command: npx skills add https://github.com/lzlatkin/dots --skill improve-lzlatkin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines the process of capturing learnings from AI sessions, improving existing skills, and updating the knowledge base to make future AI interactions more effective.

Core Features & Use Cases

  • Skill Refinement: Identifies and proposes improvements to AI skills based on session interactions.
  • Knowledge Capture: Extracts durable knowledge from conversations and adds it to a structured knowledge base.
  • Codebase Gap Identification: Detects and suggests fixes for missing documentation, tests, or configuration in codebases.
  • Use Case: After a complex debugging session, run /improve to automatically document the solution, update the relevant skill to handle similar issues in the future, and capture the root cause in the project's knowledge base.

Quick Start

Run /improve at the end of any session to capture learnings and suggest skill improvements.

Frequently Asked Questions about improve

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I capture session learnings to improve AI agent capabilities?

To capture session learnings for AI agent capabilities, run a post-session analysis command to automatically extract durable knowledge from conversation history and add it to a structured knowledge base. This automates continuous improvement of your AI workflows.

What is the best way to identify codebase gaps like missing documentation after a debugging session?

The best way to identify codebase gaps like missing documentation is to run a post-session analysis on your conversation history and codebase context. This detects missing tests or configuration and suggests actionable fixes automatically.

How does automated skill refinement work for AI workflows?

Automated skill refinement works by analyzing session interactions against existing skill definitions to identify weaknesses. It then proposes actionable changes to existing AI skills to handle similar issues more effectively in the future.

Can I use post-session analysis for continuous knowledge management without manual entry?

Yes, you can use post-session analysis for continuous knowledge management without manual entry. The process analyzes conversation history and automatically extracts durable knowledge to update your project's structured knowledge base.

Do I need to provide conversation history and codebase context for automated knowledge capture?

Yes, providing conversation history and codebase context is required for automated knowledge capture. The tool requires these inputs to accurately analyze session interactions and propose actionable changes to skills and documentation.

When should I run continuous improvement commands on my AI sessions?

You should run continuous improvement commands at the end of any complex AI session. This ensures that debugging solutions, root causes, and codebase gap fixes are automatically documented and applied to future agent capabilities.